Fufka commited on
Commit
4c3ff13
·
verified ·
1 Parent(s): 9df1224

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - SanjiWatsuki/Kunoichi-DPO-v2-7B
8
+ - Nondzu/zephyr-7b-beta-pl
9
+ ---
10
+
11
+ # Kunoichi-zephyr-pl-7B
12
+
13
+ Kunoichi-zephyr-pl-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
15
+ * [Nondzu/zephyr-7b-beta-pl](https://huggingface.co/Nondzu/zephyr-7b-beta-pl)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
23
+ layer_range: [0, 32]
24
+ - sources:
25
+ - model: Nondzu/zephyr-7b-beta-pl
26
+ layer_range: [24, 32]
27
+ merge_method: passthrough
28
+ dtype: bfloat16
29
+
30
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Nondzu/zephyr-7b-beta-pl",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.2",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
5
+ layer_range: [0, 32]
6
+ - sources:
7
+ - model: Nondzu/zephyr-7b-beta-pl
8
+ layer_range: [24, 32]
9
+ merge_method: passthrough
10
+ dtype: bfloat16
11
+
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f8ca0300fdd97e1d781131c0b625bfc941632840c6763bb168b915952f5155
3
+ size 1946219040
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1107f59bca226d6cd651e0670ce406329c1b191624e404f74649c5195739c4c9
3
+ size 1946243920
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9a48b09ec6e02f83a86e3fcac204ef49c90cd6740d7203e851fab075d851dc
3
+ size 1950412264
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5383c9b50c91fdc7d8d664d6ae29a486c27512055a1ace9a20b402620ecc05
3
+ size 1979789744
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2714e601a10ba0dac5bd0b4f1321caf883d064575c315772a0a9b6634dcfdb
3
+ size 1912681584
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828db7b5c6519e308b44bf1a9c02ae93f9cf2715dd4bc92f0135e10fa487b5f0
3
+ size 1979781456
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9e360d305a7402a6fb013f42adbaa9c7501fc527172392a065e7209fe9ec1d
3
+ size 1979806360
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f970b5d13fa88508824ac716ee36f2048729b95295749783c1bea11db63d2e
3
+ size 1946235688
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021aa4e4ed7716090d5c391dfaefb869b3ec7b5cd5b8ae7e2a95cd6078e27656
3
+ size 1979798048
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82670b35430bfdcdfabf197da71657483a9d520ef17b3c8798b92b8fafa7f482
3
+ size 352330200
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.embed_tokens.weight": "model-00003-of-00010.safetensors", "lm_head.weight": "model-00003-of-00010.safetensors", "model.norm.weight": "model-00003-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00010.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "truncation_side": "left",
46
+ "trust_remote_code": false,
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true,
49
+ "use_fast": true
50
+ }